@inproceedings{gupta-etal-2020-semi,
title = "A Semi-supervised Approach to Generate the Code-Mixed Text using Pre-trained Encoder and Transfer Learning",
author = "Gupta, Deepak and
Ekbal, Asif and
Bhattacharyya, Pushpak",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.206",
doi = "10.18653/v1/2020.findings-emnlp.206",
pages = "2267--2280",
abstract = "Code-mixing, the interleaving of two or more languages within a sentence or discourse is ubiquitous in multilingual societies. The lack of code-mixed training data is one of the major concerns for the development of end-to-end neural network-based models to be deployed for a variety of natural language processing (NLP) applications. A potential solution is to either manually create or crowd-source the code-mixed labelled data for the task at hand, but that requires much human efforts and often not feasible because of the language specific diversity in the code-mixed text. To circumvent the data scarcity issue, we propose an effective deep learning approach for automatically generating the code-mixed text from English to multiple languages without any parallel data. In order to train the neural network, we create synthetic code-mixed texts from the available parallel corpus by modelling various linguistic properties of code-mixing. Our codemixed text generator is built upon the encoder-decoder framework, where the encoder is augmented with the linguistic and task-agnostic features obtained from the transformer based language model. We also transfer the knowledge from a neural machine translation (NMT) to warm-start the training of code-mixed generator. Experimental results and in-depth analysis show the effectiveness of our proposed code-mixed text generation on eight diverse language pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2020-semi">
<titleInfo>
<title>A Semi-supervised Approach to Generate the Code-Mixed Text using Pre-trained Encoder and Transfer Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-mixing, the interleaving of two or more languages within a sentence or discourse is ubiquitous in multilingual societies. The lack of code-mixed training data is one of the major concerns for the development of end-to-end neural network-based models to be deployed for a variety of natural language processing (NLP) applications. A potential solution is to either manually create or crowd-source the code-mixed labelled data for the task at hand, but that requires much human efforts and often not feasible because of the language specific diversity in the code-mixed text. To circumvent the data scarcity issue, we propose an effective deep learning approach for automatically generating the code-mixed text from English to multiple languages without any parallel data. In order to train the neural network, we create synthetic code-mixed texts from the available parallel corpus by modelling various linguistic properties of code-mixing. Our codemixed text generator is built upon the encoder-decoder framework, where the encoder is augmented with the linguistic and task-agnostic features obtained from the transformer based language model. We also transfer the knowledge from a neural machine translation (NMT) to warm-start the training of code-mixed generator. Experimental results and in-depth analysis show the effectiveness of our proposed code-mixed text generation on eight diverse language pairs.</abstract>
<identifier type="citekey">gupta-etal-2020-semi</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.206</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.206</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2267</start>
<end>2280</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Semi-supervised Approach to Generate the Code-Mixed Text using Pre-trained Encoder and Transfer Learning
%A Gupta, Deepak
%A Ekbal, Asif
%A Bhattacharyya, Pushpak
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F gupta-etal-2020-semi
%X Code-mixing, the interleaving of two or more languages within a sentence or discourse is ubiquitous in multilingual societies. The lack of code-mixed training data is one of the major concerns for the development of end-to-end neural network-based models to be deployed for a variety of natural language processing (NLP) applications. A potential solution is to either manually create or crowd-source the code-mixed labelled data for the task at hand, but that requires much human efforts and often not feasible because of the language specific diversity in the code-mixed text. To circumvent the data scarcity issue, we propose an effective deep learning approach for automatically generating the code-mixed text from English to multiple languages without any parallel data. In order to train the neural network, we create synthetic code-mixed texts from the available parallel corpus by modelling various linguistic properties of code-mixing. Our codemixed text generator is built upon the encoder-decoder framework, where the encoder is augmented with the linguistic and task-agnostic features obtained from the transformer based language model. We also transfer the knowledge from a neural machine translation (NMT) to warm-start the training of code-mixed generator. Experimental results and in-depth analysis show the effectiveness of our proposed code-mixed text generation on eight diverse language pairs.
%R 10.18653/v1/2020.findings-emnlp.206
%U https://aclanthology.org/2020.findings-emnlp.206
%U https://doi.org/10.18653/v1/2020.findings-emnlp.206
%P 2267-2280
Markdown (Informal)
[A Semi-supervised Approach to Generate the Code-Mixed Text using Pre-trained Encoder and Transfer Learning](https://aclanthology.org/2020.findings-emnlp.206) (Gupta et al., Findings 2020)
ACL